Session

Beyond Code Sharing: Building Smarter Mobile Apps with KMP and Agents (with Koog, Gemini and More)

For years we’ve talked about code sharing with Kotlin Multiplatform (KMP). This talk explores the next frontier: integrating AI agents directly into your KMP architecture to create intelligent, context-aware mobile applications.

We’ll walk through building a practical cross-platform mobile app (Android + iOS) from a single KMP codebase, and show how to embed an intelligent agent using Koog. The focus is on how agents become a first-class architectural element in mobile apps—bridging local intelligence, cloud reasoning, and structured workflows.

Key themes of the session include:

Koog fundamentals: defining tools, intents, and structured actions so an agent can operate safely and predictably inside your KMP app.

On-device intelligence: combining Gemini Nano, MediaPipe GenAI, and ML Kit/Vision APIs for OCR, classification, summarization, and lightweight inference—keeping apps fast, private, and responsive.

Cloud-based reasoning: leveraging Gemini models via Vertex AI to handle semantic understanding, summarization, and fallback cases when on-device heuristics aren’t enough.

Production pragmatism: lessons learned from shipping KMP at scale—covering performance, security, observability, and how to balance on-device vs. cloud intelligence.

By the end, you’ll have a clear blueprint for:

Embedding Koog agents into a Kotlin Multiplatform app.

Using Gemini Nano, MediaPipe, and ML Kit for fast, offline inference.

Scaling up with Vertex AI + Gemini for richer reasoning.

Designing apps that feel truly intelligent and multiplatform, not just code-shared.

This isn’t theory—we’ll ground it in a working, useful app that shows the stack in action, but the real takeaway will be the architecture and technologies you can apply to your own projects.

A practical deep dive into building production-grade Kotlin Multiplatform apps—this time with agents at the core. Learn how Koog enables structured agent workflows, how Gemini and Vertex AI extend reasoning in the cloud, and how on-device ML with Gemini Nano, MediaPipe, and ML Kit keeps apps responsive and privacy-first.

Rivu Chakraborty

Android & Kotlin GDE, Author, Speaker, Enterpreneur

Bengaluru, India

Actions

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top